Merge pull request #28 from softwaresaved/dev

Dev

.gitignore

@@ -29,7 +29,8 @@ fuji_server/helper/catalogue_helper_google_datasearch_copy.py
 fuji_server/helper/create_google_cache_db_copy.py
 
 # private config
-fuji_server/config/github.cfg
+fuji_server/config/github.ini
+fuji_server/data/github_api_tokens.txt
 
 # Created by https://www.gitignore.io/api/python,linux,macos
 

README.md

@@ -102,6 +102,28 @@ If you receive the exception `urllib2.URLError: <urlopen error [SSL: CERTIFICATE
 
 F-UJI is using [basic authentication](https://en.wikipedia.org/wiki/Basic_access_authentication), so username and password have to be provided for each REST call which can be configured in `fuji_server/config/users.py`.
 
+#### GitHub API
+
+F-UJI can optionally use the GitHub API to evaluate software repositories hosted on GitHub.
+Unauthorised requests to the GitHub API are subject to a very low rate limit however, so it's recommended to authenticate using a personal access token.
+
+To create an access token, log into your GitHub account and navigate to <https://github.com/settings/tokens>, either by clicking on the link or through Settings -> Developer Settings -> Personal access tokens -> Tokens (classic). Next, click "Generate new token" and select "Generate new token (classic)" from the drop-down menu.
+
+Write the purpose of the token into the "Note" field (for example, *F-UJI deployment*) and set a suitable expiration date. Leave all the checkboxes underneath *unchecked*.
+
+> Note: When the token expires, you will receive an e-mail asking you to renew it if you still need it. The e-mail will provide a link to do so, and you will only need to change the token in the f-uji configuration as described below to continue using it. Setting no expiration date for a token is thus not recommended.
+
+When you click "Generate new token" at the bottom of the page, the new token will be displayed. Make a note of it now.
+
+To use F-UJI with a single access token, open [`fuji_server/config/github.ini`](./fuji_server/config/github.ini) locally and set `token` to the token you just created. When F-UJI receives an evaluation request that uses the GitHub API, it will run this request authenticated as your account.
+
+If you still run into rate limiting issues, you can use multiple GitHub API tokens.
+These need to be generated by different GitHub accounts, as the rate limit applies to the user, not the token.
+F-UJI will automatically switch to another token if the rate limit is near.
+To do so, create a local file in [`fuji_server/data/`](./fuji_server/data/), called e.g. `github_api_tokens.txt`. Put all API tokens in that file, one token on each line. Then, open [`fuji_server/config/github.ini`](./fuji_server/config/github.ini) locally and set `token_file` to the absolute path to your local API token file.
+
+> Note: If you push a change containing a GitHub API token, GitHub will usually recognise this and invalidate the token immediately. You will need to regenerate the token. Please take care not to publish your API tokens anywhere. Even though they have very limited scope if you leave all the checkboxes unchecked during creation, they can allow someone else to run a request in your name.
+
 ## Development
 
 First, make sure to read the [contribution guidelines](./CONTRIBUTING.md).
@@ -140,6 +162,7 @@ server {
     location ~ \.php$ {
         include snippets/fastcgi-php.conf;
         fastcgi_pass unix:/var/run/php/php8.1-fpm.sock;
+        fastcgi_read_timeout 3600s;
      }
 
     location ~ /\.ht {

fuji_server/__init__.py

@@ -8,11 +8,17 @@
 from __future__ import absolute_import
 
 # import models into model package
+from fuji_server.models.api import API
+from fuji_server.models.api_output import APIOutput
 from fuji_server.models.any_of_fair_results_results_items import AnyOfFAIRResultsResultsItems
 from fuji_server.models.body import Body
+from fuji_server.models.code_provenance import CodeProvenance
+from fuji_server.models.code_provenance_output import CodeProvenanceOutput
 from fuji_server.models.community_endorsed_standard import CommunityEndorsedStandard
 from fuji_server.models.community_endorsed_standard_output import CommunityEndorsedStandardOutput
 from fuji_server.models.community_endorsed_standard_output_inner import CommunityEndorsedStandardOutputInner
+from fuji_server.models.component_identifier import ComponentIdentifier
+from fuji_server.models.component_identifier_output import ComponentIdentifierOutput
 from fuji_server.models.core_metadata import CoreMetadata
 from fuji_server.models.core_metadata_output import CoreMetadataOutput
 from fuji_server.models.data_access_level import DataAccessLevel
@@ -27,6 +33,8 @@
 from fuji_server.models.data_provenance_output import DataProvenanceOutput
 from fuji_server.models.data_provenance_output_inner import DataProvenanceOutputInner
 from fuji_server.models.debug import Debug
+from fuji_server.models.development_metadata import DevelopmentMetadata
+from fuji_server.models.development_metadata_output import DevelopmentMetadataOutput
 from fuji_server.models.fair_result_common import FAIRResultCommon
 from fuji_server.models.fair_result_common_score import FAIRResultCommonScore
 from fuji_server.models.fair_result_evaluation_criterium import FAIRResultEvaluationCriterium
@@ -55,6 +63,8 @@
 from fuji_server.models.related_resource import RelatedResource
 from fuji_server.models.related_resource_output import RelatedResourceOutput
 from fuji_server.models.related_resource_output_inner import RelatedResourceOutputInner
+from fuji_server.models.requirements import Requirements
+from fuji_server.models.requirements_output import RequirementsOutput
 from fuji_server.models.searchable import Searchable
 from fuji_server.models.searchable_output import SearchableOutput
 from fuji_server.models.semantic_vocabulary import SemanticVocabulary
@@ -64,8 +74,14 @@
 from fuji_server.models.standardised_protocol_data_output import StandardisedProtocolDataOutput
 from fuji_server.models.standardised_protocol_metadata import StandardisedProtocolMetadata
 from fuji_server.models.standardised_protocol_metadata_output import StandardisedProtocolMetadataOutput
+from fuji_server.models.test_case import TestCase
+from fuji_server.models.test_case_output import TestCaseOutput
+from fuji_server.models.unique_persistent_identifier_software import UniquePersistentIdentifierSoftware
+from fuji_server.models.unique_persistent_identifier_software_output import UniquePersistentIdentifierSoftwareOutput
 from fuji_server.models.uniqueness import Uniqueness
 from fuji_server.models.uniqueness_output import UniquenessOutput
+from fuji_server.models.version_identifier import VersionIdentifier
+from fuji_server.models.version_identifier_output import VersionIdentifierOutput
 
 from importlib.metadata import version
 

fuji_server/config/github.ini

@@ -1,3 +1,5 @@
 [ACCESS]
 # set equal to access token if available to increase rate limit (usually starts with 'ghp_')
 token =
+# absolute path to file with tokens, optional for rotating through multiple tokens
+token_file =

fuji_server/controllers/fair_check.py

@@ -12,14 +12,18 @@
 import pandas as pd
 
 from fuji_server import __version__
+from fuji_server.evaluators.fair_evaluator_api import FAIREvaluatorAPI
+from fuji_server.evaluators.fair_evaluator_code_provenance import FAIREvaluatorCodeProvenance
 from fuji_server.evaluators.fair_evaluator_community_metadata import FAIREvaluatorCommunityMetadata
 from fuji_server.evaluators.fair_evaluator_data_access_level import FAIREvaluatorDataAccessLevel
 from fuji_server.evaluators.fair_evaluator_data_content_metadata import FAIREvaluatorDataContentMetadata
 from fuji_server.evaluators.fair_evaluator_data_identifier_included import FAIREvaluatorDataIdentifierIncluded
 from fuji_server.evaluators.fair_evaluator_data_provenance import FAIREvaluatorDataProvenance
+from fuji_server.evaluators.fair_evaluator_development_metadata import FAIREvaluatorDevelopmentMetadata
 from fuji_server.evaluators.fair_evaluator_file_format import FAIREvaluatorFileFormat
 from fuji_server.evaluators.fair_evaluator_formal_metadata import FAIREvaluatorFormalMetadata
 from fuji_server.evaluators.fair_evaluator_license import FAIREvaluatorLicense
+from fuji_server.evaluators.fair_evaluator_license_file import FAIREvaluatorLicenseFile
 from fuji_server.evaluators.fair_evaluator_metadata_identifier_included import FAIREvaluatorMetadataIdentifierIncluded
 from fuji_server.evaluators.fair_evaluator_metadata_preservation import FAIREvaluatorMetadataPreserved
 from fuji_server.evaluators.fair_evaluator_minimal_metadata import FAIREvaluatorCoreMetadata
@@ -28,14 +32,21 @@
     FAIREvaluatorPersistentIdentifierMetadata,
 )
 from fuji_server.evaluators.fair_evaluator_related_resources import FAIREvaluatorRelatedResources
+from fuji_server.evaluators.fair_evaluator_requirements import FAIREvaluatorRequirements
 from fuji_server.evaluators.fair_evaluator_searchable import FAIREvaluatorSearchable
 from fuji_server.evaluators.fair_evaluator_semantic_vocabulary import FAIREvaluatorSemanticVocabulary
+from fuji_server.evaluators.fair_evaluator_software_component_identifier import FAIREvaluatorSoftwareComponentIdentifier
 from fuji_server.evaluators.fair_evaluator_standardised_protocol_data import FAIREvaluatorStandardisedProtocolData
 from fuji_server.evaluators.fair_evaluator_standardised_protocol_metadata import (
     FAIREvaluatorStandardisedProtocolMetadata,
 )
+from fuji_server.evaluators.fair_evaluator_test_cases import FAIREvaluatorTestCases
 from fuji_server.evaluators.fair_evaluator_unique_identifier_data import FAIREvaluatorUniqueIdentifierData
 from fuji_server.evaluators.fair_evaluator_unique_identifier_metadata import FAIREvaluatorUniqueIdentifierMetadata
+from fuji_server.evaluators.fair_evaluator_unique_persistent_identifier_software import (
+    FAIREvaluatorUniquePersistentIdentifierSoftware,
+)
+from fuji_server.evaluators.fair_evaluator_version_identifier import FAIREvaluatorVersionIdentifier
 from fuji_server.harvester.data_harvester import DataHarvester
 from fuji_server.harvester.github_harvester import GithubHarvester
 from fuji_server.harvester.metadata_harvester import MetadataHarvester
@@ -352,7 +363,7 @@ def harvest_all_data(self):
 
     def harvest_github(self):
         if self.use_github:
-            github_harvester = GithubHarvester(self.id)
+            github_harvester = GithubHarvester(self.id, self.logger)
             github_harvester.harvest()
             self.github_data = github_harvester.data
         else:
@@ -442,6 +453,34 @@ def check_unique_persistent_metadata_identifier(self):
         # self.metadata_harvester.get_signposting_object_identifier()
         return self.check_unique_metadata_identifier(), self.check_persistent_metadata_identifier()
 
+    def check_unique_persistent_software_identifier(self):
+        unique_persistent_identifier_check = FAIREvaluatorUniquePersistentIdentifierSoftware(self)
+        return unique_persistent_identifier_check.getResult()
+
+    def check_software_component_identifier(self):
+        component_identifier_check = FAIREvaluatorSoftwareComponentIdentifier(self)
+        return component_identifier_check.getResult()
+
+    def check_version_identifier(self):
+        version_identifier_check = FAIREvaluatorVersionIdentifier(self)
+        return version_identifier_check.getResult()
+
+    def check_development_metadata(self):
+        development_metadata_check = FAIREvaluatorDevelopmentMetadata(self)
+        return development_metadata_check.getResult()
+
+    def check_open_api(self):
+        open_api_check = FAIREvaluatorAPI(self)
+        return open_api_check.getResult()
+
+    def check_requirements(self):
+        requirements_check = FAIREvaluatorRequirements(self)
+        return requirements_check.getResult()
+
+    def check_test_cases(self):
+        test_cases_check = FAIREvaluatorTestCases(self)
+        return test_cases_check.getResult()
+
     def check_minimal_metatadata(self, include_embedded=True):
         core_metadata_check = FAIREvaluatorCoreMetadata(self)
         return core_metadata_check.getResult()
@@ -462,6 +501,10 @@ def check_license(self):
         license_check = FAIREvaluatorLicense(self)
         return license_check.getResult()
 
+    def check_license_file(self):
+        license_check = FAIREvaluatorLicenseFile(self)
+        return license_check.getResult()
+
     def check_relatedresources(self):
         related_check = FAIREvaluatorRelatedResources(self)
         return related_check.getResult()
@@ -482,6 +525,10 @@ def check_data_provenance(self):
         data_prov_check = FAIREvaluatorDataProvenance(self)
         return data_prov_check.getResult()
 
+    def check_code_provenance(self):
+        code_prov_check = FAIREvaluatorCodeProvenance(self)
+        return code_prov_check.getResult()
+
     def check_data_content_metadata(self):
         data_content_metadata_check = FAIREvaluatorDataContentMetadata(self)
         return data_content_metadata_check.getResult()
@@ -496,7 +543,6 @@ def check_semantic_vocabulary(self):
 
     def check_metadata_preservation(self):
         metadata_preserved_check = FAIREvaluatorMetadataPreserved(self)
-        metadata_preserved_check.set_metric("FsF-A2-01M")
         return metadata_preserved_check.getResult()
 
     def check_standardised_protocol_data(self):

fuji_server/controllers/fair_object_controller.py

@@ -90,6 +90,7 @@ async def assess_by_id(body):
         access_level_result = ft.check_data_access_level()
         # print('F-UJI checks: license')
         license_result = ft.check_license()
+        license_file_result = ft.check_license_file()
         # print('F-UJI checks: related')
         related_resources_result = ft.check_relatedresources()
         # print('F-UJI checks: searchable')
@@ -98,16 +99,24 @@ async def assess_by_id(body):
         ft.harvest_all_data()
         uid_data_result = ft.check_unique_content_identifier()
         pid_data_result = ft.check_persistent_data_identifier()
+        upid_software_result = ft.check_unique_persistent_software_identifier()
+        software_component_result = ft.check_software_component_identifier()
+        version_identifier_result = ft.check_version_identifier()
+        development_metadata_result = ft.check_development_metadata()
+        open_api_result = ft.check_open_api()
+        requirements_result = ft.check_requirements()
+        test_cases_result = ft.check_test_cases()
         data_identifier_included_result = ft.check_data_content_metadata()
         metadata_identifier_included_result = ft.check_metadata_identifier_included_in_metadata()
         data_file_format_result = ft.check_data_file_format()
         # print('F-UJI checks: data file format')
         community_standards_result = ft.check_community_metadatastandards()
         data_provenance_result = ft.check_data_provenance()
+        code_provenance_result = ft.check_code_provenance()
         formal_metadata_result = ft.check_formal_metadata()
         # print('F-UJI checks: semantic vocab')
         semantic_vocab_result = ft.check_semantic_vocabulary()
-        ft.check_metadata_preservation()
+        metadata_preserved_result = ft.check_metadata_preservation()
         standard_protocol_data_result = ft.check_standardised_protocol_data()
         standard_protocol_metadata_result = ft.check_standardised_protocol_metadata()
         if uid_result:
@@ -118,6 +127,20 @@ async def assess_by_id(body):
             results.append(uid_data_result)
         if pid_data_result:
             results.append(pid_data_result)
+        if upid_software_result:
+            results.append(upid_software_result)
+        if software_component_result:
+            results.append(software_component_result)
+        if version_identifier_result:
+            results.append(version_identifier_result)
+        if development_metadata_result:
+            results.append(development_metadata_result)
+        if open_api_result:
+            results.append(open_api_result)
+        if requirements_result:
+            results.append(requirements_result)
+        if test_cases_result:
+            results.append(test_cases_result)
         if core_metadata_result:
             results.append(core_metadata_result)
         if content_identifier_included_result:
@@ -136,10 +159,14 @@ async def assess_by_id(body):
             results.append(metadata_identifier_included_result)
         if license_result:
             results.append(license_result)
+        if license_file_result:
+            results.append(license_file_result)
         if access_level_result:
             results.append(access_level_result)
         if data_provenance_result:
             results.append(data_provenance_result)
+        if code_provenance_result:
+            results.append(code_provenance_result)
         if community_standards_result:
             results.append(community_standards_result)
         if data_file_format_result:
@@ -148,6 +175,8 @@ async def assess_by_id(body):
             results.append(standard_protocol_data_result)
         if standard_protocol_metadata_result:
             results.append(standard_protocol_metadata_result)
+        if metadata_preserved_result:
+            results.append(metadata_preserved_result)
         debug_messages = ft.get_log_messages_dict()
         # ft.logger_message_stream.flush()
         summary = ft.get_assessment_summary(results)
@@ -178,6 +207,7 @@ async def assess_by_id(body):
         if ft.pid_url:
             idhelper = IdentifierHelper(ft.pid_url)
             request["normalized_object_identifier"] = idhelper.get_normalized_id()
+        results.sort(key=lambda d: d["id"])  # sort results by metric ID
         final_response = FAIRResults(
             request=request,
             start_timestamp=starttimestmp,

fuji_server/data/software_file.json

@@ -0,0 +1,58 @@
+{
+  "Jenkinsfile": {
+    "category": [
+      "automation"
+    ],
+    "parse": "full",
+    "pattern": [
+      "(\\w*/)*Jenkinsfile"
+    ]
+  },
+  "README": {
+    "category": [
+      "documentation"
+    ],
+    "parse": "full",
+    "pattern": [
+      "(\\w*/)*README(\\.(txt|md))?"
+    ]
+  },
+  "docs_directory": {
+    "category": [
+      "documentation"
+    ],
+    "parse": "file_name",
+    "pattern": [
+      "(\\w*/)*docs(/\\w*\\.\\w*)*"
+    ]
+  },
+  "github_actions": {
+    "category": [
+      "automation"
+    ],
+    "parse": "full",
+    "pattern": [
+      "\\.github/workflows/"
+    ]
+  },
+  "license_file": {
+    "category": [
+      "provenance"
+    ],
+    "parse": "full",
+    "pattern": [
+      "(\\w*/)*LICEN(S|C)E(\\.\\w*)?",
+      "(\\w*/)*licen(s|c)e(\\.\\w*)?"
+    ]
+  },
+  "maven_pom": {
+    "category": [
+      "documentation",
+      "automation"
+    ],
+    "parse": "full",
+    "pattern": [
+      "pom\\.xml"
+    ]
+  }
+}

fuji_server/evaluators/fair_evaluator.py

@@ -112,7 +112,7 @@ def isTestDefined(self, testid):
         else:
             self.logger.debug(
                 self.metric_identifier
-                + " : This test is not defined in the metric YAML and therefore not performed -: "
+                + " : This test is not defined in the metric YAML and therefore not performed: "
                 + str(testid)
             )
             return False